Skip to main content

Jorg Lucke: Linear and Non-linear Approaches to Component Extraction and Their Applications to Visual Data

Movies Preview

movies
Jorg Lucke: Linear and Non-linear Approaches to Component Extraction and Their Applications to Visual Data


Published December 13, 2010


Talk by Jorg Lucke of FIAS. Given to the Redwood Center for Theoretical Neuroscience at UC Berkeley.

Abstract.
In the nervous system of humans and animals, sensory data are represented as combinations of elementary data components. While for data such as sound waveforms the elementary components combine linearly, other data can better be modelled by non-linear forms of component superpositions. I motivate and discuss two models with binary latent variables: one using standard linear superpositions of basis functions and one using non-linear superpositions. Crucial for the applicability of both models are efficient learning procedures. I briefly introduce a novel training scheme (ET) and show how it can be applied to probabilistic generative models. For linear and non-linear models the scheme efficiently infers the basis functions as well as the level of sparseness and data noise. In large-scale applications to image patches, we show results on the statistics of inferred model parameters. Differences between the linear and non-linear models are discussed, and both models are compared to results of standard approaches in the literature and to experimental findings. Finally, I briefly discuss learning in a recent model that takes explicit component occlusions into account.


Audio/Visual sound, color

comment
Reviews

There are no reviews yet. Be the first one to write a review.
SIMILAR ITEMS (based on metadata)
Community Video
movies
eye 215
favorite 0
comment 0
Arxiv.org
texts
eye 15
favorite 0
comment 0
Source: http://arxiv.org/abs/1209.1222v1
Arxiv.org
texts
eye 21
favorite 0
comment 0
Source: http://arxiv.org/abs/1209.4580v2
Community Video
movies
eye 266
favorite 0
comment 0
University of Toronto - Gerstein Science Information Centre
by Luckiesh, Matthew, 1883-
texts
eye 641
favorite 0
comment 0
Cornell University Library
by Luckiesh, Matthew, b. 1883
texts
eye 893
favorite 0
comment 0
American Libraries
by Luckiesh, Matthew, b. 1883
texts
eye 896
favorite 0
comment 0
Source: http://books.google.com/books?id=j1pKAAAAMAAJ&oe=UTF-8
American Libraries
by Luckiesh, Matthew, b. 1883
texts
eye 1,327
favorite 1
comment 0
Source: http://books.google.com/books?id=QgYW8bqIYL4C&oe=UTF-8
California Digital Library
by Luckiesh, Matthew, b. 1883
texts
eye 993
favorite 0
comment 0